© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69513
    Prev
    Next
    INDEX
    Explanations

    multi-line comments and documentation headers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umber
    -0.06
    eme
    -0.06
     Sk
    -0.06
     Bott
    -0.06
    ual
    -0.06
     Lump
    -0.06
    olon
    -0.06
    447
    -0.06
    234
    -0.05
    437
    -0.05
    POSITIVE LOGITS
    Campo
    0.09
    _FC
    0.08
    ATIO
    0.08
    mani
    0.07
    ensa
    0.07
    adolu
    0.07
    idot
    0.07
    à¸Ńà¸Ń
    0.07
    ìĤ¬ìĿ´
    0.07
    AXB
    0.07
    Activations Density 0.002%

    No Known Activations